Search Results for author:
Found 16 papers, 13 papers with code
Learning Lightweight Lane Detection CNNs by Self Attention Distillation
Training deep models for lane detection is challenging due to the very subtle and sparse supervisory signals inherent in lane annotations.
Ranked #5 on
Lane Detection
on BDD100K val
Learning to Simulate Self-Driven Particles System with Coordinated Policy Optimization
Self-Driven Particles (SDP) describe a category of multi-agent systems common in everyday life, such as flocking birds and traffic flows.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Network Pruning via Resource Reallocation
Channel pruning is broadly recognized as an effective approach to obtain a small compact model through eliminating unimportant channels from a large cumbersome network.
TSIT: A Simple and Versatile Framework for Image-to-Image Translation
We introduce a simple and versatile framework for image-to-image translation.
Graph Structured Network for Image-Text Matching
The GSMN explicitly models object, relation and attribute as a structured phrase, which not only allows to learn correspondence of object, relation and attribute separately, but also benefits to learn fine-grained correspondence of structured phrase.
Ranked #16 on
Cross-Modal Retrieval
on Flickr30k
SNAS: Stochastic Neural Architecture Search
In experiments on CIFAR-10, SNAS takes less epochs to find a cell architecture with state-of-the-art accuracy than non-differentiable evolution-based and reinforcement-learning-based NAS, which is also transferable to ImageNet.
Ranked #25 on
Neural Architecture Search
on NAS-Bench-201, CIFAR-10
DSNAS: Direct Neural Architecture Search without Parameter Retraining
We argue that given a computer vision task for which a NAS method is expected, this definition can reduce the vaguely-defined NAS evaluation to i) accuracy of this task and ii) the total computation consumed to finally obtain a model with satisfying accuracy.
Ranked #16 on
Neural Architecture Search
on NAS-Bench-201, ImageNet-16-120
(Accuracy (Val) metric)
Understanding the wiring evolution in differentiable neural architecture search
To this end, we pose questions that future differentiable methods for neural wiring discovery need to confront, hoping to evoke a discussion and rethinking on how much bias has been enforced implicitly in existing NAS methods.
Improving the Generalization of End-to-End Driving through Procedural Generation
We validate that training with the increasing number of procedurally generated scenes significantly improves the generalization of the agent across scenarios of different traffic densities and road networks.
Inter-Region Affinity Distillation for Road Marking Segmentation
We study the problem of distilling knowledge from a large deep teacher network to a much smaller student network for the task of road marking segmentation.
Ranked #1 on
Semantic Segmentation
on ApolloScape
Learning to Steer by Mimicking Features from Heterogeneous Auxiliary Networks
In this paper, we considerably improve the accuracy and robustness of predictions through heterogeneous auxiliary networks feature mimicking, a new and effective training method that provides us with much richer contextual signals apart from steering direction.
Ranked #1 on
Steering Control
on BDD100K val
Overcoming Language Priors with Self-supervised Learning for Visual Question Answering
Our method can compensate for the data biases by generating balanced data without introducing external annotations.
Safe Driving via Expert Guided Policy Optimization
Offline RL technique is further used to learn from the partial demonstration generated by the expert.
NADPEx: An on-policy temporally consistent exploration method for deep reinforcement learning
Reinforcement learning agents need exploratory behaviors to escape from local optima.
Learning a Decision Module by Imitating Driver's Control Behaviors
In this work, we propose a hybrid framework to learn neural decisions in the classical modular pipeline through end-to-end imitation learning.
Channel-wise Alignment for Adaptive Object Detection
Existing methods on this task usually draw attention on the high-level alignment based on the whole image or object of interest, which naturally, cannot fully utilize the fine-grained channel information.
